1 / 9

Discriminative Segment Annotation in Weakly Labeled Video

Discriminative Segment Annotation in Weakly Labeled Video. Kevin Tang, Rahul Sukthankar Appeared in CVPR 2013 (Oral). Research Problem. Input : a weakly labeled video ( eg ., “dog”)

tambre
Download Presentation

Discriminative Segment Annotation in Weakly Labeled Video

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Discriminative Segment Annotation in Weakly Labeled Video Kevin Tang, Rahul Sukthankar Appeared in CVPR 2013 (Oral)

  2. Research Problem • Input: a weakly labeled video (eg., “dog”) • Output: identify segments that correspond to the label to generate the semantic segmentation, i.e., classify each segment either as coming from concept “dog” (called concept segments), or not (called background segments). • Pipeline • Perform unsupervised spatiotemporal segmentation. • Propose an algorithm to identify the meaningful segment.

  3. Contributions • Present a interpretation framework to analyze a broad class of existing weakly supervised learning algorithms about segment annotation problem. • Propose a discriminative algorithm CRANE (Concept Ranking According to Negative Exemplars) for segment annotation.

  4. Interpretation framework • Pairwise distance matrix between segments Segment: spatiotemporal volume (3D), represented as a point in feature space (such as RGB histogram, local binary pattern histogram, or dense optical histogram). • Positive segment • Concept segment • Background segment • Negative segment Goal: classify the from in . Rank the elements in in decreasing order of a score, such that top-ranked Elements correspond to .

  5. Interpretation framework • Baseline algorithms about segment annotation. • Kernel density estimation for Negative segments. • Intuition: the distribution of is similar to distribution of . • Construct a probability density operated on block C. • Rank the elements according to . • Negative Mining (MIN) • Intuition: distance from to the nearest > distance from to nearest . • Operated on block D.

  6. CRANE • Each negative segment in penalizes nearby segments in . • Segments in should be those far from negatives. Penalty function

  7. CRANE • Advantages Robust to noise. Parallelizable.

  8. Experimental Results YouTube Objects datasets

  9. Experimental Results • (a): Sucesses (b): Failures

More Related